Final_Project - Regression and Classification A
Binghan Zheng
3/29/2022
SetUp
#Libraries
library(tidyverse)## -- Attaching packages --------------------------------------- tidyverse 1.3.1 --## v ggplot2 3.3.5 v purrr 0.3.4
## v tibble 3.1.6 v dplyr 1.0.8
## v tidyr 1.2.0 v stringr 1.4.0
## v readr 2.1.2 v forcats 0.5.1## -- Conflicts ------------------------------------------ tidyverse_conflicts() --
## x dplyr::filter() masks stats::filter()
## x dplyr::lag() masks stats::lag()library(fastDummies)## Warning: package 'fastDummies' was built under R version 4.1.3library(caret)## Loading required package: lattice##
## Attaching package: 'caret'## The following object is masked from 'package:purrr':
##
## lift#Preparing the Data
df_all <- readr::read_csv("final_project_train.csv", col_names = TRUE)## Rows: 677 Columns: 38
## -- Column specification --------------------------------------------------------
## Delimiter: ","
## chr (3): region, customer, outcome
## dbl (35): rowid, xb_01, xb_02, xb_03, xn_01, xn_02, xn_03, xa_01, xa_02, xa_...
##
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.df_all <- dummy_cols(df_all, select_columns = 'region')
df_all <- dummy_cols(df_all, select_columns = 'customer')
df_all$log_response <- log(df_all$response)
df_all<-df_all %>%
mutate(outcome = ifelse(outcome == 'event', 1,0))
df_all## # A tibble: 677 x 51
## rowid region customer xb_01 xb_02 xb_03 xn_01 xn_02 xn_03 xa_01 xa_02 xa_03
## <dbl> <chr> <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 1 XX B 4 4 4 3 3 3 12 12 12
## 2 3 XX B 1 1 1 2 2 2 3 3 3
## 3 4 XX B 2 2 2 2 4 0 9 9 9
## 4 5 XX B 2.52 11 -6 1.53 9 -3 7.08 29 -7
## 5 8 XX B 2.55 6 -1 0.839 3 -4 6.45 17 -2
## 6 9 XX B 3.07 6 1 1.86 8 -2 6.86 18 2
## 7 11 XX B 3.09 10 -4 1.51 6 -5 7.66 24 -9
## 8 14 XX B 3.71 12 -4 1.59 10 -6 8.16 27 -5
## 9 15 XX B 2.70 9 -2 1.17 10 -3 6.89 20 -3
## 10 16 XX B 2.82 10 -4 1.02 4 -5 7.14 19 -3
## # ... with 667 more rows, and 39 more variables: xb_04 <dbl>, xb_05 <dbl>,
## # xb_06 <dbl>, xb_07 <dbl>, xb_08 <dbl>, xn_04 <dbl>, xn_05 <dbl>,
## # xn_06 <dbl>, xn_07 <dbl>, xn_08 <dbl>, xa_04 <dbl>, xa_05 <dbl>,
## # xa_06 <dbl>, xa_07 <dbl>, xa_08 <dbl>, xw_01 <dbl>, xw_02 <dbl>,
## # xw_03 <dbl>, xs_01 <dbl>, xs_02 <dbl>, xs_03 <dbl>, xs_04 <dbl>,
## # xs_05 <dbl>, xs_06 <dbl>, response <dbl>, outcome <dbl>, region_XX <int>,
## # region_YY <int>, region_ZZ <int>, customer_A <int>, customer_B <int>, ...#Model 1 Categorical Linear Additive
mod1 <- lm( log_response ~ region_XX + region_YY + region_ZZ + customer_A + customer_B + customer_D + customer_E + customer_G + customer_K + customer_M + customer_Other + customer_Q, data = df_all)#Model 2 Continuous: Linear Additive
mod2 <- lm( log_response ~ xa_01 +
xa_02 + xa_03 + xa_04 + xa_05 + xa_06 + xa_07 + xa_08 +
xb_01 + xb_02 + xb_03 + xb_04 + xb_05 + xb_06 + xb_07 + xb_08 +
xs_01 + xs_02 + xs_03 + xs_04 + xs_05 + xs_06 +
xn_01 + xn_02 + xn_03 + xn_04 + xn_05 + xn_06 + xn_07 + xn_08 +
xw_01 + xw_02 + xw_03 , data = df_all)#Model 3: Categorial and Continuous Linear Additive
mod3 <- lm( response ~
region_XX + region_YY + region_ZZ +
customer_A + customer_B + customer_D + customer_E + customer_G + customer_K + customer_M +
customer_Other + customer_Q + xa_01 +
xa_02 + xa_03 + xa_04 + xa_05 + xa_06 + xa_07 + xa_08 +
xb_01 + xb_02 + xb_03 + xb_04 + xb_05 + xb_06 + xb_07 + xb_08 +
xs_01 + xs_02 + xs_03 + xs_04 + xs_05 + xs_06 +
xn_01 + xn_02 + xn_03 + xn_04 + xn_05 + xn_06 + xn_07 + xn_08 +
xw_01 + xw_02 + xw_03, data = df_all)#Model 4: Categorical vs Continuous Interactions Linear Additive: Region
mod4 <- lm( log_response ~
(xa_01 + xa_02 + xa_03 + xa_04 + xa_05 + xa_06 + xa_07 + xa_08 + xb_01 + xb_02 + xb_03 + xb_04 + xb_05 + xb_06 + xb_07 + xb_08 + xs_01 + xs_02 + xs_03 + xs_04 + xs_05 + xs_06 + xn_01 + xn_02 + xn_03 + xn_04 + xn_05 + xn_06 + xn_07 + xn_08 + xw_01 + xw_02 + xw_03) *
(region_XX + region_YY + region_ZZ), data = df_all)#Model 5: Categorical vs Continuous Interactions Linear Additive: Customer
mod5 <- lm( log_response ~
(xa_01 +xa_02 + xa_03 + xa_04 + xa_05 + xa_06 + xa_07 + xa_08 + xb_01 + xb_02 + xb_03 + xb_04 + xb_05 + xb_06 + xb_07 + xb_08 + xs_01 + xs_02 + xs_03 + xs_04 + xs_05 + xs_06 + xn_01 + xn_02 + xn_03 + xn_04 + xn_05 + xn_06 + xn_07 + xn_08 + xw_01 + xw_02 + xw_03) *
(customer_A + customer_B + customer_D + customer_E + customer_G + customer_K + customer_M + customer_Other + customer_Q), data = df_all)#Model 6: All Pairwise Interaction
mod6 <- lm( log_response ~ (xa_01 +
xa_02 + xa_03 + xa_04 + xa_05 + xa_06 + xa_07 + xa_08 +
xb_01 + xb_02 + xb_03 + xb_04 + xb_05 + xb_06 + xb_07 + xb_08 +
xs_01 + xs_02 + xs_03 + xs_04 + xs_05 + xs_06 +
xn_01 + xn_02 + xn_03 + xn_04 + xn_05 + xn_06 + xn_07 + xn_08 +
xw_01 + xw_02 + xw_03)^2 , data = df_all)#Model 7
df_a <- 3
df_b <- 3
df_s <- 3
df_n <- 3
df_w <- 3
mod7 <- lm( log_response ~
splines::ns(xa_01, df_a) + splines::ns(xa_02, df_a) + splines::ns(xa_03, df_a) +
splines::ns(xa_04, df_a) +
splines::ns(xa_05, df_a) + splines::ns(xa_06, df_a) + splines::ns(xa_07, df_a) +
splines::ns(xa_08, df_a) +
splines::ns(xb_01, df_b) + splines::ns(xb_02, df_b) + splines::ns(xb_03, df_b) +
splines::ns(xb_04, df_b) +
splines::ns(xb_05, df_b) + splines::ns(xb_06, df_b) + splines::ns(xb_07, df_b) +
splines::ns(xb_08, df_b) +
splines::ns(xs_01, df_s) + splines::ns(xs_02, df_s) + splines::ns(xs_03, df_s) +
splines::ns(xs_04, df_s) +
splines::ns(xs_05, df_s) + splines::ns(xs_06, df_s) +
splines::ns(xn_01, df_n) + splines::ns(xn_02, df_n) + splines::ns(xn_03, df_n) +
splines::ns(xn_04, df_n) +
splines::ns(xn_05, df_n) + splines::ns(xn_06, df_n) + splines::ns(xn_07, df_n) +
splines::ns(xn_08, df_n) +
splines::ns(xw_01, df_w) + splines::ns(xw_02, df_w) + splines::ns(xw_03, df_w),
data = df_all)#Model 8 - Splines Interact Customer
df_a <- 3
df_b <- 3
df_s <- 3
df_n <- 3
df_w <- 3
mod8 <- lm( log_response ~
(splines::ns(xa_01, df_a) + splines::ns(xa_02, df_a) +
splines::ns(xa_03, df_a) + splines::ns(xa_04, df_a) +
splines::ns(xa_05, df_a) + splines::ns(xa_06, df_a) +
splines::ns(xa_07, df_a) + splines::ns(xa_08, df_a) +
splines::ns(xb_01, df_b) + splines::ns(xb_02, df_b) +
splines::ns(xb_03, df_b) + splines::ns(xb_04, df_b) +
splines::ns(xb_05, df_b) + splines::ns(xb_06, df_b) +
splines::ns(xb_07, df_b) + splines::ns(xb_08, df_b) +
splines::ns(xs_01, df_s) + splines::ns(xs_02, df_s) +
splines::ns(xs_03, df_s) + splines::ns(xs_04, df_s) +
splines::ns(xs_05, df_s) + splines::ns(xs_06, df_s) +
splines::ns(xn_01, df_n) + splines::ns(xn_02, df_n) +
splines::ns(xn_03, df_n) + splines::ns(xn_04, df_n) +
splines::ns(xn_05, df_n) + splines::ns(xn_06, df_n) +
splines::ns(xn_07, df_n) + splines::ns(xn_08, df_n) +
splines::ns(xw_01, df_w) + splines::ns(xw_02, df_w) +
splines::ns(xw_03, df_w)) *
(customer_A + customer_B + customer_D + customer_E + customer_G +
customer_K + customer_M + customer_Other + customer_Q),
data = df_all)#Model 9 - Splines Interact Region
df_a <- 3
df_b <- 3
df_s <- 3
df_n <- 3
df_w <- 3
mod9 <- lm( log_response ~
(splines::ns(xa_01, df_a) +splines::ns(xa_02, df_a) + splines::ns(xa_03, df_a) + splines::ns(xa_04, df_a) +
splines::ns(xa_05, df_a) + splines::ns(xa_06, df_a) + splines::ns(xa_07, df_a) + splines::ns(xa_08, df_a) +
splines::ns(xb_01, df_b) + splines::ns(xb_02, df_b) + splines::ns(xb_03, df_b) + splines::ns(xb_04, df_b)+ splines::ns(xb_05, df_b) + splines::ns(xb_06, df_b) + splines::ns(xb_07, df_b) + splines::ns(xb_08, df_b) +
splines::ns(xs_01, df_s) + splines::ns(xs_02, df_s) + splines::ns(xs_03, df_s) + splines::ns(xs_04, df_s) +
splines::ns(xs_05, df_s) + splines::ns(xs_06, df_s) +
splines::ns(xn_01, df_n) + splines::ns(xn_02, df_n) + splines::ns(xn_03, df_n) + splines::ns(xn_04, df_n) +
splines::ns(xn_05, df_n) + splines::ns(xn_06, df_n) + splines::ns(xn_07, df_n) + splines::ns(xn_08, df_n) +
splines::ns(xw_01, df_w) + splines::ns(xw_02, df_w) + splines::ns(xw_03, df_w)) *
(region_XX + region_YY + region_ZZ),
data = df_all)#Model Evaluation
mod_performace<-bind_rows(
broom::glance(mod1),
broom::glance(mod2),
broom::glance(mod3),
broom::glance(mod4),
broom::glance(mod5),
broom::glance(mod6),
broom::glance(mod7),
broom::glance(mod8),
broom::glance(mod9))
mod_performace## # A tibble: 9 x 12
## r.squared adj.r.squared sigma statistic p.value df logLik AIC BIC
## <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 0.182 0.170 0.487 14.8 4.93e- 24 10 -468. 961. 1015.
## 2 0.542 0.519 0.371 23.1 1.16e- 87 33 -272. 614. 772.
## 3 0.525 0.493 1.25 16.3 3.20e- 76 43 -1086. 2263. 2466.
## 4 0.727 0.679 0.303 15.2 6.28e-110 101 -96.7 399. 865.
## 5 0.821 0.679 0.303 5.79 3.41e- 55 299 46.1 510. 1870.
## 6 0.924 0.556 0.357 2.51 6.53e- 9 561 338. 451. 2994.
## 7 0.619 0.554 0.357 9.47 1.30e- 72 99 -210. 622. 1078.
## 8 0.932 0.711 0.288 4.21 1.27e- 22 517 373. 291. 2636.
## 9 0.839 0.711 0.288 6.56 2.32e- 62 299 81.3 439. 1799.
## # ... with 3 more variables: deviance <dbl>, df.residual <int>, nobs <int>##Top 3 Model Coef Plot
#Best Model
- Performance Metric Used in Determining the best models: R-Squared.
Reasoning: I want to focus around determining the strength of the correlation between the predictors and the response. In focusing around these models of high r-squared values, we can also narrow down those predictors which are most significant of which, according to the plot(varImp(mod8)) are:
# Mod 8
coefplot::coefplot(mod8)
#Second Best Model
# Mod 6
coefplot::coefplot(mod6)
#Third Best Model
# Mod 4
coefplot::coefplot(mod9)
How do coefficient summaries compare between the 3 models?
- All of the coefficient summaries between the 3 models contain many variables which are not statistically significant yet do contain intervals which are very wide ranging and highly uncertain. Our best model, mod 8, does contain smaller intervals around 0, but are still not entirely significant. I will next utilize
trainin determining those variables which were important and noteworthy enough in the best model, mod8.
Which inputs seem important?
- Let’s find out with some quick tests
set.seed(12345)
my_ctrl <- caret::trainControl(method = "repeatedcv",
number = 5,
repeats = 3,
savePredictions = TRUE)
my_metric <- "Rsquared"mod8<- train(log_response ~
(splines::ns(xa_01, 3) + splines::ns(xa_02, 3) +
splines::ns(xa_03, 3) + splines::ns(xa_04, 3) +
splines::ns(xa_05, 3) + splines::ns(xa_06, 3) +
splines::ns(xa_07, 3) + splines::ns(xa_08, 3) +
splines::ns(xb_01, 3) + splines::ns(xb_02, 3) +
splines::ns(xb_03, 3) + splines::ns(xb_04, 3) +
splines::ns(xb_05, 3) + splines::ns(xb_06, 3) +
splines::ns(xb_07, 3) + splines::ns(xb_08, 3) +
splines::ns(xs_01, 3) + splines::ns(xs_02, 3) +
splines::ns(xs_03, 3) + splines::ns(xs_04, 3) +
splines::ns(xs_05, 3) + splines::ns(xs_06, 3) +
splines::ns(xn_01, 3) + splines::ns(xn_02, 3) +
splines::ns(xn_03, 3) + splines::ns(xn_04, 3) +
splines::ns(xn_05, 3) + splines::ns(xn_06, 3) +
splines::ns(xn_07, 3) + splines::ns(xn_08, 3) +
splines::ns(xw_01, 3) + splines::ns(xw_02, 3) +
splines::ns(xw_03, 3)) *
(customer_A + customer_B + customer_D + customer_E + customer_G +
customer_K + customer_M + customer_Other + customer_Q),
data = df_all,
method = "lm",
metric = my_metric,
preProcess = c("center" , "scale"),
trControl = my_ctrl,
trace = FALSE)plot(varImp(mod8), top = 10)
- Those continuous variables which were significantly important in our model are in descending order: xs_02, xs_01, xa_03 and xb_08. These four are repeated multiple times and I will consider these variables to be our most important inputs.
###CLASSIFICATION
#Model 1: Categorical Linear Additive
mod1 <- glm( outcome ~ region_XX + region_YY + region_ZZ + customer_A + customer_B + customer_D + customer_E + customer_G + customer_K + customer_M + customer_Other + customer_Q, family = "binomial", data = df_all)#Model 2: Continuous Linear Additive
mod2 <- glm( outcome ~ xa_01 +
xa_02 + xa_03 + xa_04 + xa_05 + xa_06 + xa_07 + xa_08 +
xb_01 + xb_02 + xb_03 + xb_04 + xb_05 + xb_06 + xb_07 + xb_08 +
xs_01 + xs_02 + xs_03 + xs_04 + xs_05 + xs_06 +
xn_01 + xn_02 + xn_03 + xn_04 + xn_05 + xn_06 + xn_07 + xn_08 +
xw_01 + xw_02 + xw_03 ,family = "binomial", data = df_all)#Model 3: Continuous and Categorical Linear Additive
mod3 <- glm( outcome ~
region_XX + region_YY + region_ZZ +
customer_A + customer_B + customer_D + customer_E + customer_G + customer_K + customer_M + customer_Other + customer_Q +
xa_01 +
xa_02 + xa_03 + xa_04 + xa_05 + xa_06 + xa_07 + xa_08 +
xb_01 + xb_02 + xb_03 + xb_04 + xb_05 + xb_06 + xb_07 + xb_08 +
xs_01 + xs_02 + xs_03 + xs_04 + xs_05 + xs_06 +
xn_01 + xn_02 + xn_03 + xn_04 + xn_05 + xn_06 + xn_07 + xn_08 +
xw_01 + xw_02 + xw_03, family = "binomial",data = df_all)#Model 4: Categorical vs Continuous Interactions Linear Additive: Region
mod4 <- glm( outcome ~
(xa_01 + xa_02 + xa_03 + xa_04 + xa_05 + xa_06 + xa_07 + xa_08) *
(region_XX + region_YY + region_ZZ) +
(xb_01 + xb_02 + xb_03 + xb_04 + xb_05 + xb_06 + xb_07 + xb_08) *
(region_XX + region_YY + region_ZZ) +
(xs_01 + xs_02 + xs_03 + xs_04 + xs_05 + xs_06)*
(region_XX + region_YY + region_ZZ) +
(xn_01 + xn_02 + xn_03 + xn_04 + xn_05 + xn_06 + xn_07 + xn_08)*
(region_XX + region_YY + region_ZZ) +
(xw_01 + xw_02 + xw_03)*
(region_XX + region_YY + region_ZZ), family = "binomial", data = df_all)#Model 5: Categorical vs Continuous Interactions Linear Additive: Customer
mod5 <- glm( outcome ~
(xa_01 +xa_02 + xa_03 + xa_04 + xa_05 + xa_06 + xa_07 + xa_08) *
(customer_A + customer_B + customer_D + customer_E + customer_G + customer_K + customer_M + customer_Other + customer_Q) +
(xb_01 + xb_02 + xb_03 + xb_04 + xb_05 + xb_06 + xb_07 + xb_08) *
(customer_A + customer_B + customer_D + customer_E + customer_G + customer_K + customer_M + customer_Other + customer_Q) +
(xs_01 + xs_02 + xs_03 + xs_04 + xs_05 + xs_06)*
(customer_A + customer_B + customer_D + customer_E + customer_G + customer_K + customer_M + customer_Other + customer_Q) +
(xn_01 + xn_02 + xn_03 + xn_04 + xn_05 + xn_06 + xn_07 + xn_08)*
(customer_A + customer_B + customer_D + customer_E + customer_G + customer_K + customer_M + customer_Other + customer_Q) +
(xw_01 + xw_02 + xw_03)*
(customer_A + customer_B + customer_D + customer_E + customer_G + customer_K + customer_M + customer_Other + customer_Q), family = "binomial",data = df_all)## Warning: glm.fit: algorithm did not converge## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred#Model 6: All Pairwise Interaction
mod6 <- glm( outcome ~ (xa_01 +
xa_02 + xa_03 + xa_04 + xa_05 + xa_06 + xa_07 + xa_08 +
xb_01 + xb_02 + xb_03 + xb_04 + xb_05 + xb_06 + xb_07 + xb_08 +
xs_01 + xs_02 + xs_03 + xs_04 + xs_05 + xs_06 +
xn_01 + xn_02 + xn_03 + xn_04 + xn_05 + xn_06 + xn_07 + xn_08 +
xw_01 + xw_02 + xw_03)^2 , family = "binomial", data = df_all)## Warning: glm.fit: algorithm did not converge## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred#Model 7: Spline of Continuous
df_a <- 2
df_b <- 2
df_s <- 2
df_n <- 2
df_w <- 2
mod7 <- glm( outcome ~
splines::ns(xa_01, df_a) +splines::ns(xa_02, df_a) + splines::ns(xa_03, df_a) + splines::ns(xa_04, df_a) +
splines::ns(xa_05, df_a) + splines::ns(xa_06, df_a) + splines::ns(xa_07, df_a) + splines::ns(xa_08, df_a) +
splines::ns(xb_01, df_b) + splines::ns(xb_02, df_b) + splines::ns(xb_03, df_b) + splines::ns(xb_04, df_b) +
splines::ns(xb_05, df_b) + splines::ns(xb_06, df_b) + splines::ns(xb_07, df_b) + splines::ns(xb_08, df_b) +
splines::ns(xs_01, df_s) + splines::ns(xs_02, df_s) + splines::ns(xs_03, df_s) + splines::ns(xs_04, df_s) +
splines::ns(xs_05, df_s) + splines::ns(xs_06, df_s) +
splines::ns(xn_01, df_n) + splines::ns(xn_02, df_n) + splines::ns(xn_03, df_n) + splines::ns(xn_04, df_n) +
splines::ns(xn_05, df_n) + splines::ns(xn_06, df_n) + splines::ns(xn_07, df_n) + splines::ns(xn_08, df_n) +
splines::ns(xw_01, df_w) + splines::ns(xw_02, df_w) + splines::ns(xw_03, df_w), family = "binomial", data = df_all)#Model 8: Spline of Continuous Interact Region
df_a <- 2
df_b <- 2
df_s <- 2
df_n <- 2
df_w <- 2
mod8 <- glm( outcome ~
(splines::ns(xa_01, df_a) +splines::ns(xa_02, df_a) + splines::ns(xa_03, df_a) + splines::ns(xa_04, df_a) +
splines::ns(xa_05, df_a) + splines::ns(xa_06, df_a) + splines::ns(xa_07, df_a) + splines::ns(xa_08, df_a) +
splines::ns(xb_01, df_b) + splines::ns(xb_02, df_b) + splines::ns(xb_03, df_b) + splines::ns(xb_04, df_b) +
splines::ns(xb_05, df_b) + splines::ns(xb_06, df_b) + splines::ns(xb_07, df_b) + splines::ns(xb_08, df_b) +
splines::ns(xs_01, df_s) + splines::ns(xs_02, df_s) + splines::ns(xs_03, df_s) + splines::ns(xs_04, df_s) +
splines::ns(xs_05, df_s) + splines::ns(xs_06, df_s) +
splines::ns(xn_01, df_n) + splines::ns(xn_02, df_n) + splines::ns(xn_03, df_n) + splines::ns(xn_04, df_n) +
splines::ns(xn_05, df_n) + splines::ns(xn_06, df_n) + splines::ns(xn_07, df_n) + splines::ns(xn_08, df_n) +
splines::ns(xw_01, df_w) + splines::ns(xw_02, df_w) + splines::ns(xw_03, df_w)) *
(customer_A + customer_B + customer_D + customer_E + customer_G + customer_K + customer_M + customer_Other + customer_Q),
family = "binomial", data = df_all)#Model 9: Spline of Continuous Interact Customer
df_a <- 2
df_b <- 2
df_s <- 2
df_n <- 2
df_w <- 2
mod9 <- glm( outcome ~
(splines::ns(xa_01, df_a) +splines::ns(xa_02, df_a) + splines::ns(xa_03, df_a) + splines::ns(xa_04, df_a) +
splines::ns(xa_05, df_a) + splines::ns(xa_06, df_a) + splines::ns(xa_07, df_a) + splines::ns(xa_08, df_a) +
splines::ns(xb_01, df_b) + splines::ns(xb_02, df_b) + splines::ns(xb_03, df_b) + splines::ns(xb_04, df_b) +
splines::ns(xb_05, df_b) + splines::ns(xb_06, df_b) + splines::ns(xb_07, df_b) + splines::ns(xb_08, df_b) +
splines::ns(xs_01, df_s) + splines::ns(xs_02, df_s) + splines::ns(xs_03, df_s) + splines::ns(xs_04, df_s) +
splines::ns(xs_05, df_s) + splines::ns(xs_06, df_s) +
splines::ns(xn_01, df_n) + splines::ns(xn_02, df_n) + splines::ns(xn_03, df_n) + splines::ns(xn_04, df_n) +
splines::ns(xn_05, df_n) + splines::ns(xn_06, df_n) + splines::ns(xn_07, df_n) + splines::ns(xn_08, df_n) +
splines::ns(xw_01, df_w) + splines::ns(xw_02, df_w) + splines::ns(xw_03, df_w)) *
(region_XX + region_YY + region_ZZ),
family = "binomial", data = df_all)#Model Evaluation
mod_performace<-bind_rows(
broom::glance(mod1),
broom::glance(mod2),
broom::glance(mod3),
broom::glance(mod4),
broom::glance(mod5),
broom::glance(mod6),
broom::glance(mod7),
broom::glance(mod8),
broom::glance(mod9))
mod_performace## # A tibble: 9 x 8
## null.deviance df.null logLik AIC BIC deviance df.residual nobs
## <dbl> <int> <dbl> <dbl> <dbl> <dbl> <int> <int>
## 1 654. 676 -3.11e+2 644. 693. 6.22e+2 666 677
## 2 654. 676 -2.14e+2 496. 650. 4.28e+2 643 677
## 3 654. 676 -2.00e+2 489. 688. 4.01e+2 633 677
## 4 654. 676 -1.86e+2 575. 1036. 3.71e+2 575 677
## 5 654. 676 -2.52e+3 5646. 7001. 5.05e+3 377 677
## 6 654. 676 -3.50e-9 1124. 3663. 7.01e-9 115 677
## 7 654. 676 -1.95e+2 524. 827. 3.90e+2 610 677
## 8 654. 676 -2.85e+3 6600. 8642. 5.70e+3 225 677
## 9 654. 676 -3.10e+3 6602. 7510. 6.20e+3 476 677##Top 3 Model Coef Plot
#Best Model
coefplot::coefplot(mod9)
#Second Best Model
# Mod 6
coefplot::coefplot(mod8)
#Third Best Model
# Mod 4
coefplot::coefplot(mod5)